Final Project Datasets

Final Project Datasets

by Isaac -

Dr. Pletcher and Team,

I'm a bit concerned about the final project. I have access to several datasets; however, the focus of my entire YEAR is to extract and clean the data (i.e. Health eHeart, Healthcare Utilization Project).

If the task of extracting and cleaning the data is too daunting or beyond the scope of this initial course, do you suggest just using publicly accessible data (e.g. NHANES) or the data from our labs (Coronary Calcium Score!) and just complete the Final Project requirements that way?

Thanks.

Re: Final Project Datasets

by Mark Pletcher -

Thanks for posting about your concerns - I suspect you're not the only one with a big, complicated dataset on your hands and not sure how you'll be able to tackle the whole thing for the Final Project.

My basic recommendation: Just bite off a small piece and work with that.  You might, for example, just do a very simple table and figure with just a couple of data elements in Health eHeart (one survey and one measurement?), so you don't need to try to clean the whole thing.  Figure out JUST the variables you'll need and clean those.

A backup plan can always be to analyze some publicly accessible dataset, BUT it is going to be more interesting and more productive for you if you can make some headway (even if only a limited amount) with a dataset that you are actually interested in using.